Longitudinal Data Structure Research Articles

Computational aspects of likelihood-based estimation of first-order antedependence models

Computational aspects of the problem of estimating the parameters of first-order antedependence models for the covariance structure of longitudinal data are considered. These models may be useful when serial correlation exists among measurements within subjects but is nonstationary. For those situations in which measurement times are common across subjects, the maximum likelihood estimators of unstructured first-order antedependent model parameters can be given explicitly. When measurement times are not identical across subjects or when the first-order antedependence model is more structured, however, the likelihood-based estimation of model parameters must be accomplished numerically and would thus appear to require extensive computations. In this article we show how this computational burden can be substantially reduced. The usefulness of the results is illustrated by analyses of longitudinal data from a IOO-km race and from a study on cochlear implants.

Analysis of longitudinal data in craniofacial research: some strategies.

Although it is generally acknowledged that longitudinal data provide the most information on growth and development and other time-dependent phenomena, such data are often analyzed by conventional (cross-sectional) statistical methods. This widespread practice ignores the distinctive characteristics (e.g., covariance structure) of longitudinal data and may yield misleading results. The purpose of this article is to present some strategies and make available computer programs for the appropriate analysis of longitudinal data. User-friendly PC programs for the estimation of average growth curves, computation of tracking indices, prediction of future values, diagnosis, classification, clustering, estimation of missing values, and testing hypotheses concerning individual and group differences are presented. Benefits of these methods over the usual techniques are illustrated with the example of maxillary growth in the rhesus monkey.

Sample size estimation using repeated measurements on biomarkers as outcomes

The objectives of this paper are to (1) examine methods of using longitudinal data in designing comparative trials and calculating sample sizes or power and (2) show the effect of autocorrelation of repeated measures on the assessment of sample sizes. A statistical model with a simple regression structure for the mean trajectory of the longitudinal data and a two-parameter model for the correlations of within-individual observations given by corr( y t , y t+ s ) = γ s θ is used. The methods are illustrated by considering a two-group trial and investigating the effect of different values of the correlation parameters, γ and θ on the sample size. The results show that taking account of the autocorrelation structure of longitudinal data may lead to more efficient designs. Specifically, the stronger the autocorrelation is, the smaller the sample size that is required.

Mixed Poisson Likelihood Regression Models for Longitudinal Interval Count Data

In many longitudinal studies it is desired to estimate and test the rate over time of a particular recurrent event. Often only the event counts corresponding to the elapsed time intervals between each subject's successive observation times, and baseline covariate data, are available. The intervals may vary substantially in length and number between subjects, so that the corresponding vectors of counts are not directly comparable. A family of Poisson likelihood regression models incorporating a mixed random multiplicative component in the rate function of each subject is proposed for this longitudinal data structure. A related empirical Bayes estimate of random-effect parameters is also described. These methods are illustrated by an analysis of dyspepsia data from the National Cooperative Gallstone Study.